International Journal of Veterinary Sciences and Animal Husbandry 2024; 9(6): 94-102

ISSN: 2456-2912
VET 2024; 9(6): 94-102
© 2024 VET
www.veterinarypaper.com
Beyond the dissection table: AI powered virtual
Received: 19-09-2024 anatomy for veterinary students
Accepted: 27-10-2024

P Abinaya P Abinaya, K Dharani, R Gnanadevi and TA Kannan

Department of Veterinary
Anatomy, Madras Veterinary
College, TANUVAS, Chennai, DOI: https://doi.org/10.22271/veterinary.2024.v9.i6b.1843
Tamil Nadu, India
Abstract
K Dharani The integration of artificial intelligence (AI) into anatomy education offers transformative potential,
Department of Veterinary providing resources that enhance both deep and logical understanding through immersive, three-
Anatomy, Madras Veterinary dimensional virtual reality experiences. These tools simulate the exploration of a living, breathing animal
College, TANUVAS, Chennai, body, contributing significantly to the comprehensive knowledge required for clinical practices in
Tamil Nadu, India
veterinary medicine and surgery. However, several challenges must be addressed for successful
R Gnanadevi
implementation. Logistical concerns, such as the costs associated with servers, educational tool
Department of Veterinary development, and technical support, pose barriers. Additionally, issues of access and equity arise, as
Anatomy, Madras Veterinary some students may lack adequate computer resources or reliable internet connectivity, limiting their
College, TANUVAS, Chennai, ability to fully engage with these technologies. Furthermore, the design of AI-based educational
Tamil Nadu, India programs must be inclusive, accommodating diverse curricula and various cultural, racial, and ethnic
contexts. Addressing these considerations is essential to ensuring AI's effective integration into anatomy
TA Kannan and medical education, enhancing learning while overcoming practical and accessibility obstacles.
Department of Veterinary
Anatomy, Madras Veterinary Keywords: Accessibility, connectivity, transformative, veterinary and virtual
College, TANUVAS, Chennai,
Tamil Nadu, India
1. Introduction
Intelligence encompasses the capacity to think critically, analyse information, learn from past
experiences, and adapt to new situations (Tirri & Nokelainen, 2011) [60]. It plays a crucial role
in shaping human experiences, involving cognitive abilities such as understanding, reasoning,
recognition, invention, planning, crisis management and communication (Colom et al., 2010)
[14].
When these cognitive functions are replicated by machines, it is known as artificial
intelligence (AI) (Collins, 2021) [13].
Artificial intelligence is a field of science focused on developing computer algorithms that
perform tasks typically requiring human intelligence. Significant advancements in AI have
been driven by innovations in artificial neural networks and deep learning. AI is broadly
defined as the creation of machines capable of exhibiting intelligent behaviour and performing
tasks that were traditionally executed by humans (McCarthy, 1955; Chan & Zary, 2019;
Russell & Norvig, 2010) [37, 9, 49]. This involves creating systems that can think, learn and make
decisions autonomously, aiming to replicate or surpass human cognitive functions.

2. Domains of AI
Artificial Intelligence (AI) comprises three primary domains:
1. Symbolic, Logic-based, and Knowledge-based AI
2. Statistical AI, which encompasses probabilistic methods and machine learning
3. Sub-symbolic AI, which includes embodied intelligence and search algorithms (Abdellatif
et al., 2022) [1].
Corresponding Author:
P Abinaya Each of these domains addresses different facets of problems, such as perception, planning,
Department of Veterinary knowledge, reasoning, and communication (Russell & Norvig, 2010). [49] Today, AI is applied
Anatomy, Madras Veterinary across various sectors, including finance, automotive engineering, economics, medicine, and
College, TANUVAS, Chennai,
Tamil Nadu, India
education (Chan & Zary, 2019) [9].
~ 94 ~
International Journal of Veterinary Sciences and Animal Husbandry https://www.veterinarypaper.com

Fig 1: Main elements of AI (Pushpa et al.,2022) [44].

2.1 Machine learning (ML) centuries (Singh et al., 2015) [55]. Often referred to as the
Machine learning (ML) is a subset of AI that is often used "mother of medical education," anatomy serves as the
interchangeably with the term AI. It allows machines to learn foundation for all clinical medical sciences. When asked
from datasets without being explicitly programmed for a about its importance, medical professionals consistently rank
specific task. (Raymond & Medina, 2018; Kulkarni et al., gross anatomy as being of paramount fundamental
2021) [47,31]. significance (Singh et al., 2015; Pabst & Rothkotter, 1997) [55,
42].
ML operates in three main ways: supervised, unsupervised, Numerous studies have shown that both medical students
and reinforcement learning. In supervised learning, the system (Singh et al., 2015; Moxham & Plaisant, 2007) [54, 39]. and
is trained using labelled data provided by humans to achieve postgraduate students recognize the critical importance of
the desired outcomes. Unsupervised learning, on the other anatomy (Singh et al., 2015; Cottam, 1999) [55, 15].
hand, involves the system working with unlabelled data, A thorough understanding of anatomy is essential for medical
uncovering patterns or structures within the data. The professionals in patient examination, understanding and
combination of these two approaches forms the basis of diagnosing diseases, and communicating effectively with
reinforcement learning, which aims to maximize precision patients and other healthcare providers. Additionally,
and accuracy by learning from feedback and rewards knowledge of anatomy is crucial for performing surgical and
(Raymond & Medina, 2018; Kulkarni et al., 2021) [47,31]. other invasive procedures. It plays a pivotal role in both
diagnosis and treatment, as a clear comprehension of normal
2.2 Deep learning (DL) anatomical structures and the deviations caused by disease
Deep learning (DL) is a highly advanced subset of machine informs therapeutic approaches (Singh et al., 2015) [55].
learning and a sophisticated branch of artificial intelligence
(AI) (Hu et al., 2020) [25]. It employs intricate neural networks 4. Teaching of veterinary anatomy
to process and interpret unstructured data, allowing systems to The approach to teaching anatomy has undergone significant
address complex problems with remarkable accuracy. In DL, changes over time. Challenges such as limited instructional
algorithms are trained using extensive datasets, enabling them time and insufficient faculty have long been concerns for
to achieve outputs that closely mimic human cognitive university educators and administrators. While some
abilities. Key applications of deep learning include institutions maintain traditional teaching methods, many have
autonomous decision-making systems, sophisticated web updated their curricula to adopt an integrated approach.
search engines, AI-powered robots, advanced natural Students often perceive anatomy lectures as monotonous and
language processing tools, and disease mapping. This unengaging, critiquing them for using outdated teaching
technology is pivotal in advancing numerous fields by techniques. Research has not identified a single superior
providing more precise and efficient solutions to complex teaching model; instead, the most effective strategy appears to
challenges (Bengio et al., 2013) [6]. involve the integration of multimodal methods into the
learning process (Wilson, 2018) [63]. This diversified approach
2.3 Chat GPT (Generative Pretrained Transformer) is considered more engaging and effective for students (Estai
ChatGPT, developed by OpenAI and based in San Francisco, & Bunt, 2016) [20].
CA, USA, represents a significant leap in artificial
intelligence technology. Released in November 2022, 4.1 Conventional methods of teaching anatomy
ChatGPT quickly attracted one million users within a few Traditional methods of teaching anatomy encompass a variety
days (Liebrenz et al., 2023; Sedaghat, 2023) [34,52].This of approaches, including didactic lectures, cadaveric
cutting-edge language model harnesses deep learning dissection, examination of prosected specimens, use of
techniques to generate human-like responses to text inputs. It anatomical models, surface anatomy, and radiological
has been trained on a comprehensive dataset derived from the anatomy.
internet, allowing it to understand and address a diverse range • Dissection involves students actively exploring
of queries in natural language. This capability enables anatomical structures in cadavers, sectioning the body
ChatGPT to participate in coherent, contextually relevant along various planes to identify specific anatomical
conversations and offer meaningful interactions. features. This hands-on method, often paired with
lectures and master classes, has been a fundamental
3. Anatomy in the veterinary profession teaching tool for over 400 years (Azer and Eizenberg,
Anatomy has been a cornerstone of medical education for 2007) [4], employing both regional and systemic

~ 95 ~
International Journal of Veterinary Sciences and Animal Husbandry https://www.veterinarypaper.com

approaches. However, it has faced criticism for being commercially available models (McMenamin et al., 2014) [38].
time-consuming and costly (Aziz et al.,2002) [5], and As 3D printers become more affordable and widely available,
some medical schools have replaced it with alternative their use in anatomical teaching is expected to grow. These
methods such as prosection combined with other teaching models are particularly beneficial for teaching intricate
modalities (Drake et al.,2009) [19]. anatomical structures, illustrating anomalies, and simulating
• Prosection allows students to study pre-dissected surgical interventions (Jaksa et al., 2021; Vatankhah et al.,
cadavers, offering an opportunity to observe real 2021; Yuan et al, 2021) [28, 61, 64].
anatomical structures without the extensive time
commitment required for dissection (Dinsmore et • Virtual Reality (VR) and Augmented Reality (AR)
al.,1999) [17].These specimens are typically displayed in Augmented Reality (AR) overlays digital information onto
anatomy museums and morphology laboratories. the real world, accessible through devices such as cameras,
• Plastination is a technique developed by Gunther von tablets, or mobile phones. In contrast, Virtual Reality (VR)
Hagens at Heidelberg University in 1977(Estai and immerses users in a completely artificial environment,
Bunt,2016) [20]. It involves the preservation of dissected effectively isolating them from the physical world (Huang et
cadaver structures, and even entire bodies, using al., 2019) [26]. Both technologies offer immersive and
chemical materials. This method provides odourless, interactive experiences that enhance the understanding of
durable anatomical preparations that do not require complex anatomical concepts.
traditional chemical preservatives, thus reducing the need
for continuous dissections. Plastinated specimens are 5. Role of ai: novel uses of artificial intelligence in
easier to handle and store, making them a practical facilitating anatomy teaching, learning, and assessment
alternative in anatomy education(Fruhstorfer et al.,2011) • Artificial Intelligence (AI), once considered a futuristic
[21]
. concept, is now an integral part of everyday life. Its
applications range from voice recognition systems like
4.2 Modern methods of teaching anatomy Alexa to the precise analysis and reporting of medical
• 3D Interactive Anatomy Teaching investigations, as well as predicting disease outcomes and
Early advancements in computer-based technology for management strategies for individual patients. AI
anatomy education introduced three-dimensional interactive technologies, such as Artificial Neural Networks (ANN)
platforms. These tools enable students to navigate through and the more advanced Convolutional Neural Networks
various layers of anatomical structures and rotate images to (CNN), are designed to mimic the neural networks of the
view them from different angles and perspectives. (Pushpa et human brain. These systems not only store, process,
al., 2022) [44]. analyse, and compute data, but also improve their
machine learning capabilities over time, effectively
• Digital Dissection "thinking" and exploring optimal solutions.
A recent innovation in anatomy education is "digital • In the realm of anatomy education, AI's capabilities
dissection," which allows students to virtually dissect the extend to facilitating teaching, learning, and assessment.
body by sequentially removing layers or specific structures. AI systems can simulate complex anatomical structures
This method simulates the experience of real-time dissection and processes, offering personalized learning experiences
sessions, offering a more interactive and accessible learning that adapt to the needs of individual students.
experience (Pushpa et al.,2022) [44]. Additionally, AI's ability to analyse large datasets and
recognize patterns enhances the accuracy of anatomical
• 3D Printing Technology assessments. The advanced functionality of AI even
The advent of 3D printing technology has provided anatomy allows for remote-controlled robotic surgeries,
educators with a new resource. 3D printed anatomical models showcasing its potential to revolutionize practice
are increasingly used in anatomy labs to complement (Ramesh, 2004) [46].
traditional methods such as dissection, prosections, and

Fig 2: Schematic diagram showing how artificial intelligence can be incorporated in anatomy teaching (Abdellatif et al., 2022) [1]

~ 96 ~
International Journal of Veterinary Sciences and Animal Husbandry https://www.veterinarypaper.com

5.1 Teaching and learning hematomas. This technique is valued for its simplicity, safety
AI plays a pivotal role in modern medical education through for both the subject and operator, portability, and rapid
intelligent tutoring systems (Qayumi & Qayumi, 1999; Primal results. It allows for immediate interpretation and diagnosis in
Pictures, 2022) [45, 43]. It bridges the gap between traditional most cases (Szencziova and Strapak, 2012) [57].
teaching methods and the digital preferences of contemporary
students by offering personalized support. AI-driven systems
can identify knowledge gaps, provide targeted feedback, and
facilitate personalized learning experiences. They also handle
administrative tasks such as attendance tracking and
assignment grading, tasks traditionally performed manually
by educators (Interact Elsevier, 2022) [27]. Despite the
advantages of AI, it is crucial to address ethical and moral
considerations when designing computer-based learning
systems and AI algorithms (Anatomage Inc., 2022; Martín,
2018) [2,35].Ensuring that these systems are transparent,
credible, auditable, and reliable is essential.
Deep learning, a subset of machine learning can analyse and
reproduce anatomical structures with high accuracy, Fig 3: Two dimensional ultrasonographic image of mammary gland
especially in complex areas such as the brain, head and neck, of lactating adult Madras Red ewe showing homogenous
and limb musculature. For instance, the Bayesian U-Net parenchyma(P) A-Alveoli (Senthilkumar, 2019) [53]
framework has demonstrated the ability to segment
musculoskelet al anatomy from CT images with exceptional
precision (Nara Institute of Science and Technology, 2019)
[40]
.This technology, if tailored to anatomical course
requirements, could serve as a valuable educational tool.
Interactive teaching aids, such as Anatomy Chatbots (Li et al.,
2021) [33], formative assessment tools, and clinical application
quizzes, can be integrated into deep learning AI frameworks
to foster deeper, logical learning and enhance students'
application of knowledge in clinical settings (Chan &
Wiseman, 2011) [10]

5.2 Personalized learning Fig 4: Two dimensional ultrasonographical image of mammary

AI-powered adaptive learning systems can pinpoint specific gland of lactating adult Boer local she-goat showing blood flow in a
areas where individual students face difficulties and offer blood vessel(arrow) P-Parenchyma (Senthilkumar,2019) [53]
targeted remediation. For example, if a student struggles with
understanding the musculoskeletal system of equines, the AI 5.3.2 Electrocardiography
system can suggest additional resources or interactive The clinical application of electrocardiography (ECG) in dogs
exercises tailored to address those specific challenges. These began with Norr's pioneering work in 1922 (Norr,1922;
AI-based learning platforms analyse student performance data Lannek,1949) [41, 32]. ECG is a non-invasive, relatively
to customize learning pathways, adapting to each student’s inexpensive method used to diagnose cardiac arrhythmias and
needs. This personalized approach enhances comprehension assess myocardial health. It detects disturbances in cardiac
and retention, ultimately leading to improved academic rate and rhythm, as well as chamber enlargement, myocardial
outcomes (Anil Choudary 2024) [3]. disease, ischemia, pericardial disease, electrolyte imbalances,
and certain drug toxicities. Consequently, ECG is a valuable
5.3 Image analysis tool in cardiac evaluation, aiding in the diagnosis of
In veterinary medicine, the accurate interpretation of medical anatomical and physiological conditions and in
images is essential for diagnosing and treating animals. AI prognostication (Tilley, 1992) [59].
algorithms, trained on extensive datasets, assist veterinarians Augustus D. Waller first demonstrated in 1887 that electrical
in identifying anatomical structures and pathological impulses from the heart could be recorded from the body's
conditions with greater efficiency. AI-based image analysis surface. Einthoven later described the P-QRS-T deflections
software supports the interpretation of radiographs and associated with the heart's excitation waves. The P wave
ultrasound images, helping students develop the skills corresponds to atrial depolarization or contraction originating
required for diagnosing various conditions in clinical practice from the sinoatrial (SA) node to the atrioventricular (AV)
(Anil Choudary 2024) [3]. node, the QRS complex represents ventricular depolarization
or contraction, and the T wave signifies ventricular
5.3.1 Ultrasonography repolarization or relaxation. ECG essentially reflects the
Ultrasonography is a non-invasive diagnostic technique used summation of multiple action potentials generated by cardiac
to assess various physiological and pathological conditions of cells across the entire heart. To view the heart from different
the reproductive organs in ruminants. It serves as an effective perspectives, multiple lead systems are used, with the
tool for diagnosing abnormalities in the udder, including standard leads (I, II, and III) being fundamental since the
inflammation, mucosal lesions, tissue proliferation, foreign inception of electrocardiography (Tilley, 1992) [59].
bodies, milk stones, congenital changes, abscesses, and

~ 97 ~
International Journal of Veterinary Sciences and Animal Husbandry https://www.veterinarypaper.com

"computed tomography" combines "computed" (referring to

the use of computers), "tomo" (meaning "to cut"), and "graph"
(meaning "pictures"). This technique employs ionizing
radiation (X-rays) in conjunction with an electronic detector
array to capture patterns of tissue densities, thereby
generating images of slices of tissue (Villifana, 1987) [62].
A CT scan produces cross-sectional images by scanning a flat,
transverse slice of the body while the patient lies on a
stationary table (Thrall, 2002) [58]. According to Rivero et al.
Fig 5: Ecg Strip of Adult Chippiparai dog showing P-QRS-T (2009) [48], veterinary computed tomography has become the
Deflections (Bhargavi, 2019) [7] preferred modality for abdominal imaging in cats and dogs,
providing a reliable depiction of cross-sectional anatomy.
5.3.3 Echocardiography
Two-dimensional real-time echocardiography (2DE),
extensively studied in humans, has only recently been applied
in veterinary medicine. Thomas (1984) proposed that a
comprehensive anatomical evaluation of the canine heart
using 2DE was feasible with a standardized, systematic
examination technique. This method captures both long-axis
(longitudinal) and short-axis (cross-sectional) views of the
heart. It identifies three transducer orientations that provide
consistent images of key cardiac structures, including all four
cardiac chambers, atrioventricular and semilunar valves, and
the proximal portions of major blood vessels. Thus, 2DE has
shown significant potential for evaluating cardiac anatomy
and physiology in dogs. Echocardiography, or cardiac Fig 8: Computed tomographic image of adult male Rajapalayam dog
ultrasound, is now considered an essential diagnostic tool in showing the stomach(St) separated by the liver (Li)from the ventral
abdominal wall and entirely located within the intra-thoracic part of
veterinary medicine. (Henik, 1995) [22].
the abdominal cavity. Gb-Gall bladder Sp-Spleen
(Senthilkumar,2023) [53]

Fig 6: Two-Dimensional Echocardiographic Image- Right Long

Axis View of Left Ventricle of Rajapalayam Dog IVS- Fig 9: Computed tomographic image of adult female Rajapalayam
Interventricular Septum; LVD-Left Ventricle Diameter; LVPW-Left dog showing the lumbar vertebrae articulated cranially with thoracic
Ventricular Posterior Wall (Bhargavi,2018) [7] vertebra and caudally with sacrum (Senthilkumar, 2023) [53]

5.3.5 Radiography
X-rays are a form of high-energy radiation within the
electromagnetic spectrum, characterized by their short
wavelength and ability to ionize cells and tissues as they pass
through the body. In radiography, X-rays are generated
through the rapid deceleration of fast-moving electrons within
an X-ray tube. The intensity and size of the X-ray beam are
controlled by adjusting the voltage and amperage applied to
the tube. Radiographic images are two-dimensional (2-D)
representations of three-dimensional structures (Dixon, 2008)
[18].

Interpreting radiographic images requires a thorough

Fig 7: Two-Dimensional Echocardiographic Image-Right Long Axis understanding of normal anatomical structures, variations, and
View of Rajapalayam Dog AOD- Aortic Root Diameter; LAD-Left their radiological appearances. Radiographs produce images
Atrial Diameter (Bhargavi,2018) [7] in black, white, and various shades of grey, reflecting
differences in X-ray beam attenuation by different tissues.
5.3.4 Computed tomography The degree of tissue absorption is influenced by the tissue's
Computed Tomography (CT) is one of the most prevalent atomic number, specific gravity, and thickness. Bone, with its
cross-sectional imaging techniques in medicine. The term higher atomic number and specific gravity, absorbs more X-

~ 98 ~
International Journal of Veterinary Sciences and Animal Husbandry https://www.veterinarypaper.com

ray photons, appearing pale or white on the radiograph. Gas, chatbot to analyse the anatomical implications of these cases,
with the lowest specific gravity, absorbs few X-rays and applying their knowledge to diagnose and propose treatment
appears black, while fat appears dark grey, soft tissue or fluid options. This method enhances critical thinking and problem-
appears mid-grey, and met al appears white (Koong, 2012) solving skills within the context of anatomy (Choudhary et
[30].
al.,2023) [11].
Abdominal radiography is particularly useful for diagnosing
conditions such as foreign body obstruction, dyschezia, 5.8 Reinforcement of key concepts
urinary incontinence, anuria, dysuria, organomegaly, and for Chatbots can support the reinforcement of key anatomical
pregnancy diagnosis in dogs and cats (Hollway and concepts through interactive tools such as quizzes, flashcards,
McConnell, 2013). [24] or review sessions. Students can assess their knowledge,
pinpoint areas of weakness, and receive immediate feedback.
This repetitive reinforcement helps solidify their
understanding of veterinary anatomy. While some features
currently available in other chatbots are not yet present in
ChatGPT, future updates could incorporate these capabilities
to enhance learning (Choudhary et al.,2023) [11].

5.9 Research and development

AI is driving advancements in veterinary anatomy by enabling
the automated analysis of large datasets and uncovering novel
insights. AI-powered tools are used to explore evolutionary
Fig 10: Left lateral digital radiographic image of Chippiparai trends and investigate disease mechanisms, significantly
showing vertebral heart score measurement LA-Long Axis;SA-Short enriching our understanding of animal anatomy and
Axis; L-Left; T1,T4-Thoracic vertebra (Bhargavi,2018) [7] physiology. For instance, AI algorithms can analyse genomic
data to identify genetic variations linked to specific
5.4 Interactive learning tools anatomical traits in domestic animals. This research not only
AI-driven interactive learning tools create engaging advances our knowledge of animal anatomy but also impacts
educational experiences that captivate student interest and breeding programs and conservation efforts (Anil Choudhary
promote active participation. By incorporating elements such 2024) [3].
as gamification, simulations, and virtual reality, these tools
enhance learning by making it both enjoyable and accessible. 5.10 Assessment
For example, virtual reality simulations enable veterinary Assessment is a critical component of medical education,
students to explore complex anatomical concepts through serving as a means to gauge student progress. Research on
immersive experiences. Students can interact with virtual anatomy assessment methodologies often focuses on indices
models of animal anatomy, gaining a more profound such as objectivity, validity, reliability, and educational
understanding of physiological processes and anatomical impact (Samarasekera et al., 2015) [50]. An assessment method
relationships (Anil Choudary 2024) [3]. that is uniform across all students, without individual bias, is
GPT-powered chatbots further enrich the learning experience universally valued. An impartial, objective approach to
by engaging in interactive conversations with students. These assessment is appreciated by the student body, as it ensures
chatbots allow students to inquire about specific anatomical that all students are evaluated on a consistent basis.
structures or systems, providing detailed descriptions, Objectivity becomes crucial when different examiners may
definitions, and explanations. This conversational approach have varying opinions on students’ knowledge and skills.
helps students better grasp the complexities of veterinary Uniformity in assessment questions and tasks helps achieve
anatomy (Choudhary et al., 2023) [11]. this objectivity, leading to greater standardization in the
expected responses, skills, and behaviours from students
5.5 Accessible reference materials (Brenner, 2014) [8].
Chatbots also offer veterinary students easy access to Despite efforts to maintain objectivity, human assessments are
anatomical information. They can quickly provide answers inherently susceptible to biases related to subject matter and
about the location, function, and clinical relevance of specific cultural factors such as gender and region. Furthermore, there
anatomical structures, which is particularly valuable during is considerable diversity in evaluating anatomical knowledge,
study sessions, practical exams, or when preparing for attitudes toward the subject, and skills. To address these
surgeries (Choudhary et al., 2023) [11]. challenges, it is essential to agree on best strategies and
methodologies to ensure reliability, consistency, validity, and
5.6 Comparative anatomy standardization (Sullivan, 2011) [56]. The integration of AI in
Veterinary anatomy often involves examining anatomical assessment processes can enhance these goals by providing
differences across animal species. Chatbots can assist in automated adjustments in difficulty levels and unbiased
comparative anatomy by delivering information about specific evaluations.
anatomical variations and emphasizing the unique features of The "assessment for learning" paradigm, which focuses on
each species. This interactive approach allows students to active and authentic assessment approaches, has been widely
explore and understand the similarities and differences adopted in medical education. This approach provides
between various animal anatomies (Choudhary et al.,2023) learners and educators with insights into their current
[11]
. progress, future goals, and the best methods to achieve them
(Klenowski,2009; Dannefer,2013) [29,16].With advancements in
5.7 Case-based learning anatomy education, including AI, modern assessment
GPT-powered chatbots can facilitate case-based learning by strategies have evolved to include competency-based
presenting scenarios or clinical cases involving anatomical assessments, portfolio-based assessments, and programmatic
abnormalities or pathologies. Students can interact with the
~ 99 ~
International Journal of Veterinary Sciences and Animal Husbandry https://www.veterinarypaper.com

assessments, which are now prevalent in many contemporary 5. Self-Review Resources: AI systems designed for self-
health-related curricula (McBride & Drake, 2018; Hift, 2014) assessment by creating interactive learning programs,
[36,23]
.However, traditional assessment methods focusing on including cause-and-effect, multiple-choice questions and
factual knowledge remain common in some medical and problem-based clinical scenarios. These tools would offer
health education disciplines, with an emphasis on summative immediate feedback and facilitate self-evaluation.
assessments (Choudhury & Freemont, 2017; Samarasekera et 6. Objective Assessment and Data Compilation: AI-
al., 2020) [12,51].Consequently, as anatomy curricula evolve, driven systems to objectively assess student performance,
anatomists must reconsider assessment methods to apply an compile statistical data on scores and grades, and
authentic approach that ensures the effective application of compare academic achievements across different cohorts
knowledge and skills, achieving a recognized level of and learning modes.
competency. 7. Interactive Clinical Training: Development of
interactive robots programmed to simulate specific
clinical conditions. These robots could respond to
interventions, allowing students to practice their clinical
and diagnostic skills in a controlled environment.
8. Complex Interactive Quizzes: AI-based apps that
generate anatomical images and advanced interactive
quizzes, enhancing self-learning opportunities and
engagement, similar to platforms like Kahoot.

7. Conclusion
To summarize, as we are in digital era, AI may be used as an
effective tool in enhancing the learner centred learning in the
discipline of Veterinary Anatomy which leads to thorough
understanding of the subject and its application in Veterinary
Medicine.

8. Acknowledgements
The authors express their gratitude to the Dean of Madras
Veterinary College, Chennai, for their encouragement and
support.

9. Competing Interests
The authors have declared that they have no competing
interests.
Fig 11: Anatomy Assessment in Era of Artificial Intelligence 10. Authors’ contributions
(Abdellatif et al., 2022) [1] This work was carried out in collaboration among all authors.
All authors read and approved the final manuscript.
6. Future novel scope of artificial intelligence in anatomy
education 11. References
As anatomists, we envision several potential developments in 1. Abdellatif H, Al Mushaiqri M, Albalushi H, Al-Zaabi
AI that could transform anatomy education (Abdellatif et al., AA, Roychoudhury S, Das S. Teaching, learning and
2022) [1]: assessing anatomy with artificial intelligence: the road to
1. Virtual Reality (VR) Apps: The creation of VR a better future. Int J Environ Res Public Health.
applications to provide a deeper understanding of 2022;19(21):14209.
complex anatomical fields such as embryology and 2. Anatomage Inc. Anatomage Table; c2022. Available
neuroscience. These apps could offer immersive from: https://www.anatomage.com/table/ (accessed on 25
experiences to explore intricate anatomical structures and August 2022).
developmental processes. 3. Choudhary A. Embracing Tomorrow: The Evolution of
2. Advanced Data Analysis: Tools for analysing, Veterinary Anatomy Teaching through Artificial
computing, and summarizing complex anatomical data. Intelligence. Acta Sci Vet Sci. 2024;6(5):1-3.
For instance, in embryology, AI could track and visualize 4. Azer SA, Eizenberg N. Do we need dissection in an
the migration and differentiation of structures across integrated problem-based learning medical course?
developmental timelines. Similarly, it could map neural Perceptions of first- and second-year students. Surg
pathways in the central nervous system, simplifying Radiol Anat. 2007 Mar;29(2):173-180.
complex topics into accessible overviews. 5. Aziz MA, McKenzie JC, Wilson JS, Cowie RJ, Ayeni
3. 3D Imaging and Printing: Development of AI tools to SA, Dunn BK. The human cadaver in the age of
enhance visual learning through detailed 3D images and biomedical informatics. Anat Rec. 2002 15;269(1):20-32.
their integration with 3D printing technology. This could 6. Bengio Y, Courville A, Vincent P. Representation
produce accurate, physical models of complex anatomical learning: A review and new perspectives. IEEE Trans
structures that are challenging to dissect. Pattern Anal Mach Intell. 2013;35:1798-828.
4. Deep Learning for Structured Demos: AI systems that 7. Bhargavi S. Anatomic Evaluation of Heart using Two-
provide detailed demonstrations of intricate anatomical dimensional Echocardiography and Radiography in
regions, such as the head, face, and neck, functioning as indigenous breeds of dogs. PG thesis submitted at
valuable teaching assistants. TANUVAS, India. 2018.

~ 100 ~
International Journal of Veterinary Sciences and Animal Husbandry https://www.veterinarypaper.com

8. Brenner E. Human body preservation - old and new 24. Hollway A, McConnell F. BSAVA Manual of Canine
techniques. J Anat. 2014;224:316-44. and Feline Radiography and Radiology: A Foundation
9. Chan KS, Zary N. Applications and challenges of Manual. 1st ed. United Kingdom: BSAVA; c2013.
implementing artificial intelligence in medical education: 25. Hu J, Niu H, Carrasco J, Lennox B, Arvin F. Voronoi-
integrative review. JMIR Med Educ. 2019;5 based multi-robot autonomous exploration in unknown
Available from: https://mededu.jmir.org/2019/1/e13930 environments via deep reinforcement learning. IEEE
10. Chan LK, Wiseman J. Use of the one-minute preceptor as Trans Veh Technol. 2020;69:14413-23.
a teaching tool in the gross anatomy laboratory. Anat Sci 26. Huang KT, Ball C, Francis J, Ratan R, Boumis J,
Educ. 2011;4:235-238. Available from: Fordham J. Augmented vs Virtual Reality in education:
https://anatomypubs.onlinelibrary.wiley.com/doi/abs/10.1 an exploratory study examining science knowledge
002/ase.234 retention when using AR/VR mobile applications.
11. Choudhary OP, Saini J, Challana A, Choudhary O, Saini Cyberpsychol Behav Soc Netw. 2019 Feb;22(2):105-10.
J, Challana A. ChatGPT for veterinary anatomy 27. Interact Elsevier. Netter’s 3D Interactive Anatomy. 2022.
education: an overview of the prospects and drawbacks. Available from: https://netter3danatomy.com/ (accessed
Int J Morphol. 2023;41(4):1198-1202. on 25 August 2022).
12. Choudhury B, Freemont A. Assessment of anatomical 28. Jaksa L, Pahr D, Kronreif G, Lorenz A. Development of
knowledge: Approaches taken by higher education a multi-material 3D printer for functional anatomic
institutions. Clin Anat. 2017;30:290-9. Available from: models. Int J Bioprint. 2021;7:420. Available from:
https://onlinelibrary.wiley.com/doi/abs/10.1002/ca.22835 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8600298
13. Collins C, Dennehy D, Conboy K, Mikalef P. Artificial /
intelligence in information systems research: a systematic 29. Klenowski V. Assessment for learning revisited: an Asia-
literature review and research agenda. Int J Inf Manag. Pacific perspective. Assess Educ Princ Pol Pract.
2021;60:102383. 2009;16:263-268. Available from:
14. Colom R, Karama S, Jung RE, Haier RJ. Human https://eprints.qut.edu.au/28741/1/28741.pdf
intelligence and brain networks. Dialogues Clin 30. Koong B. The basic principles of radiological
Neurosci. 2010;12:489-501. interpretation. Aust Dent J. 2012;57(1):33-39.
15. Cottam WW. Adequacy of medical school gross anatomy 31. Kulkarni P, Mahadevappa M, Chilakamarri S. The
education as perceived by certain postgraduate residency emergence of artificial intelligence in cardiology: current
programs and anatomy course directors. Clin Anat. and future applications. Curr Cardiol Rev.
1999;12:55-65. Available from: 2021;10.2174/1573403X17666211119102220.
https://onlinelibrary.wiley.com/doi/abs/10.1002/(SICI)10 32. Lannek N. A clinical and experimental study of the
98-2353(1999)12:1%3C55::AID-CA8%3E3.0.CO;2-O electrocardiogram in dogs [thesis]. Stockholm; c1949.
16. Dannefer EF. Beyond assessment of learning toward 33. Li YS, Lam CSN, See C. Using a machine learning
assessment for learning: educating tomorrow’s architecture to create an AI-powered chatbot for anatomy
physicians. Med Teach. 2013;35:560-563. Available education. Med Sci Educ. 2021;31:1729-1730. Available
from: from:
https://www.tandfonline.com/doi/abs/10.3109/0142159X. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8651944
2013.787141 /
17. Dinsmore CE, Daugherty S, Zeitz HJ. Teaching and 34. Liebrenz M, Schleifer R, Buadze A, Bhugra D, Smith A.
learning gross anatomy: dissection, prosection, or both of Generating scholarly content with ChatGPT: ethical
the above? Clin Anat. 1999;12(2):110-4. challenges for medical publishing. Lancet Digit Health.
18. Dixon AM. Fundamentals of Diagnostic Imaging: An 2023;5(3)
Introduction for Nurses and Allied Health Professionals. 35. Martín JG, Mora CD, Henche SA. Possibilities for the
Exeter: Reflect Pets Ltd; c2008. use of anatomage (the anatomical real body-size table)
19. Drake RL, McBride JM, Lachman N, Pawlina W. for teaching and learning anatomy with the students.
Medical education in the anatomical sciences: the winds Biomed J Sci Tech Res. 2018;4:4080-4083. Available
of change continue to blow. Anat Sci Educ. 2009 from: https://www.researchgate.net/profile/Jesus-Garcia-
Dec;2(6):253-9. Martin-
20. Estai M, Bunt S. Best teaching practices in anatomy 2/publication/350775565_Possibilities_for_the_use_of_A
education: a critical review. Ann Anat. 2016;208:151- natomage_the_Anatomical_Real_Body-
157. Available from: Size_Table_for_Teaching_and_Learning_Anatomy_with
https://www.sciencedirect.com/science/article/pii/S09409 _the_Students_Mini_Review_Open_Access/links/6070fc
60216300322?casa_token=_EVgI3PMhesAAAAA:Z7Or 774585150fe9980eca/Possibilities-for-the-use-of-
W4tXppM6xx_2505MnakFvrdM5BRznn5DzAp6YowO Anatomage-the-Anatomical-Real-Body-Size-Table-for-
TCmKV20Vui8Wgq-QvsIlbwX0sHRG-sg Teaching-and-Learning-Anatomy-with-the-Students-
21. Fruhstorfer BH, Palmer J, Brydges S, Abrahams PH. The Mini-Review-Open-Access.pdf
use of plastinated prosections for teaching anatomy: the 36. McBride JM, Drake RL. National survey on anatomical
view of medical students on the value of this learning sciences in medical education. Anat Sci Educ. 2018;11:7-
resource. Clin Anat. 2011 Mar;24(2):246-52. 14. Available from:
22. Henik RA. Manual of Canine and Feline Cardiology. 2nd https://anatomypubs.onlinelibrary.wiley.com/doi/abs/10.1
ed. Philadelphia: W.B. Saunders Company; c1995. p. 75- 002/ase.1760
107. 37. McCarthy J, Minsky ML, Rochester N, Shannon CE. A
23. Hift RJ. Should essays and other “open-ended”-type Proposal for the Dartmouth Summer Research Project on
questions retain a place in written summative assessment Artificial Intelligence, August 31, 1955. AI Magazine. 31
in clinical medicine? BMC Med Educ. 2014;14:249. December 2016. Available from:
Available from: http://ojs.aaai.org/aimagazine/index.php/aimagazine/artic
https://link.springer.com/content/pdf/10.1186/s12909- le/view/1904 (accessed on 25 August 2022)
014-0249-2.pdf
~ 101 ~
International Journal of Veterinary Sciences and Animal Husbandry https://www.veterinarypaper.com

38. McMenamin PG, Quayle MR, McHenry CR, Adams JW. 52. Sedaghat S. Early applications of ChatGPT in medical
The production of anatomical teaching resources using practice, education, and research. Clin Med (Lond).
three-dimensional (3D) printing technology. Anat Sci 2023;23(3):278-279.
Educ. 2014;7:479-486. Available from: 53. Senthil Kumar S. Anatomical, histological and
https://anatomypubs.onlinelibrary.wiley.com/doi/abs/10.1 ultrasonographical studies of mammary gland in small
002/ase.1475 ruminants. PG thesis submitted at TANUVAS, India.
39. Moxham BJ, Plaisant O. Perception of medical students 2019.
towards the clinical relevance of anatomy. Clin Anat. 54. Senthil Kumar S. Computed tomographic anatomy of
2007;20:560-564. Available from: abdomen in indigenous breeds of dogs. PhD thesis
https://onlinelibrary.wiley.com/doi/abs/10.1002/ca.20453 submitted at TANUVAS, India. 2023.
40. Nara Institute of Science and Technology. Artificial 55. Singh R, Tubbs RS, Gupta K, Singh M, Jones DG,
Intelligence Learns Muscle Anatomy in CT Images. Kumar R. Is the decline of human anatomy hazardous to
Science Daily. 31 October 2019. Available from: medical education/profession?—A review. Surg Radiol
www.sciencedaily.com/releases/2019/10/191031100526. Anat. 2015;37:1257-1265. Available from:
htm (accessed on 25 August 2022). https://www.researchgate.net/profile/David-Jones-
41. Norr J. Uber Herzstromkurvebaufnahmen an Haustieren. 165/publication/278787458
Zur Einführung der Elektrokardiographie in die 56. Sullivan GM. A primer on the validity of assessment
Veterinarmedizin. Arch Tierheilk. 1922;48:85-111. instruments. J Grad Med Educ. 2011;3:119-120.
42. Pabst R, Rothkotter HJ. Retrospective evaluation of 57. Szencziova I, Strapak P. Ultrasonography of the udder
undergraduate medical education by doctors at the end of and teat in cattle: perspective measuring technique.
their residency time in hospitals: consequences for the Slovak J Anim Sci. 2012;45(3):96-104.
anatomical curriculum. Anat Rec. 1997;249:431-434. 58. Thrall DE. Textbook of Veterinary Diagnostic
Available from: Radiology. 4th ed. Saunders; c2002. p. 65.
https://anatomypubs.onlinelibrary.wiley.com/doi/pdfdirec 59. Tilley LP. Essentials of Canine and Feline
t/10.1002/%28SICI%291097- Electrocardiography: Interpretation and Treatment. 3rd
0185%28199712%29249%3A4%3C431%3A%3AAID- ed. Lea & Febiger; Philadelphia; c1992. p. 1-60.
AR1%3E3.0.CO%3B2-U 60. Tirri K, Nokelainen P. Measuring multiple intelligences
43. Primal Pictures. The Leading 3D Anatomy Resource. and moral sensitivities in education. In: Moral
2022. Available from: https://www.primalpictures.com/ Development and Citizenship Education. Rotterdam,
(accessed on 25 August 2022). Netherlands: Sense Publishers; c2011.
44. Pushpa NB, Patra A, Ravi KS. Will artificial intelligence 61. Vatankhah R, Emadzadeh A, Nekooei ST, Yousefi BT,
assume a role in anatomy education? Natl J Clin Anat. Rezaiyan MK, Moonaghi HK, et al. 3D printed models
2022;11(2):65-67. for teaching orbital anatomy, anomalies, and fractures. J
45. Qayumi AK, Qayumi T. Computer-assisted learning: Ophthalmic Vis Res. 2021;16:611-619. Available from:
Cyberpatient—A step in the future of surgical education. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8593539
J Investig Surg. 1999;12:307-317. Available from: /
https://www.can-health.org/wp- 62. Villifana T. Physics and instrumentation: CT and MRI.
content/uploads/2015/05/Computer-ASsisted-Learning- In: Lee SH, Rao KCVG, editors. Cranial Computed
CyberPatient-A-Step-in-the-Future-of-Surgical- Tomography and MRI. 2nd ed. New York: McGraw-Hill;
Education.pdf c1987. p. 7. Available from:
46. Ramesh AN, Kambhampati C, Monson JR, Drew PJ. https://inis.iaea.org/search/search.aspx?orig_q=RN:20034
Artificial intelligence in medicine. Ann R Coll Surg Engl. 978
2004;86:334-338. 63. Wilson AB, Miller CH, Klein BA, Taylor MA, Goodwin
47. Raymond JL, Medina JF. Computational principles of M, Boyle EK, Brown K, Hoppe C, Lazarus M. A meta-
supervised learning in the cerebellum. Annu Rev analysis of anatomy laboratory pedagogies. Clin Anat.
Neurosci. 2018;41:233-253. 2018;31:122-133. Available from:
48. Rivero MA, Vázquez JM, Gil F, Ramírez JA, Vilar JM, https://research.monash.edu/files/239998967/53594771_
Miguel AD, Arenbica A. CT-soft tissue window of the oa.pdf
cranial abdomen in clinically normal dogs: an anatomical 64. Yuan ZM, Zhang XD, Wu SW, Nian ZZ, Liao J, Lin W,
description using macroscopic cross-sections with Zhuang LM. A simple and convenient 3D printed
vascular injection. Anat Histol Embryol. 2009;38:18-22. temporal bone model for drilling simulating surgery.
49. Russell S, Norvig P. Artificial Intelligence: A Modern Acta Otolaryngol. 2021;142:19-22. Available from:
Approach. 3rd ed. Harlow, UK: Pearson Education https://www.tandfonline.com/doi/abs/10.1080/00016489.
Limited; c2010. Available from: 2021.2015079.
https://zoo.cs.yale.edu/classes/cs470/materials/aima2010.
pdf (accessed on 25 August 2022). How to Cite This Article
Abinaya P, Dharani K, Gnanadevi R, Kannan TA. Beyond the
50. Samarasekera DD, Gopalakirshnakone P, Gwee MC. dissection table: AI powered virtual anatomy for veterinary students.
Assessing anatomy as a basic medical science. In: Chan International Journal of Veterinary Sciences and Animal Husbandry.
LK, Pawlina W, editors. Teaching Anatomy: A Practical 2024;9(6):94-102.
Guide. 1st ed. New York, NY: Springer International
Publishing; c2015. p. 279-289. Creative Commons (CC) License
51. Samarasekera DD, Ang ET, Gwee MC. Assessing This is an open access journal, and articles are distributed under the
anatomy as a basic medical science. In: Teaching terms of the Creative Commons Attribution-NonCommercial-
Anatomy: A Practical Guide. 2nd ed. Chan LK, Pawlina ShareAlike 4.0 International (CC BY-NC-SA 4.0) License, which
W, editors. Cham, Switzerland: Springer Nature allows others to remix, tweak, and build upon the work non-
commercially, as long as appropriate credit is given and the new
Switzerland AG; c2020. p. 393-404. creations are licensed under the identical terms.

~ 102 ~