Visual interpretability in 3D brain tumor segmentation network

Saleem, Hira; Raza, Basit

doi:10.1016/j.compbiomed.2021.104410

Cited by 42 publications

(28 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The development of autonomous brain tumor segmentation and classification models using MRI images is still a challenging task. The challenges are due to several constraints including the effect of different types of noises embedded in the brain MRI images [ 116 , 117 , 118 ], motion and metal artifacts during image acquisition [ 164 ], low-resolution MRI images [ 165 ], and lack of deep learning models interpretability and transparency [ 166 , 167 ].…”

Section: Discussionmentioning

confidence: 99%

A Survey of Brain Tumor Segmentation and Classification Algorithms

Biratu

Schwenker

Ayano³

et al. 2021

J. Imaging

View full text Add to dashboard Cite

A brain Magnetic resonance imaging (MRI) scan of a single individual consists of several slices across the 3D anatomical view. Therefore, manual segmentation of brain tumors from magnetic resonance (MR) images is a challenging and time-consuming task. In addition, an automated brain tumor classification from an MRI scan is non-invasive so that it avoids biopsy and make the diagnosis process safer. Since the beginning of this millennia and late nineties, the effort of the research community to come-up with automatic brain tumor segmentation and classification method has been tremendous. As a result, there are ample literature on the area focusing on segmentation using region growing, traditional machine learning and deep learning methods. Similarly, a number of tasks have been performed in the area of brain tumor classification into their respective histological type, and an impressive performance results have been obtained. Considering state of-the-art methods and their performance, the purpose of this paper is to provide a comprehensive survey of three, recently proposed, major brain tumor segmentation and classification model techniques, namely, region growing, shallow machine learning and deep learning. The established works included in this survey also covers technical aspects such as the strengths and weaknesses of different approaches, pre- and post-processing techniques, feature extraction, datasets, and models’ performance evaluation metrics.

show abstract

Section: Discussionmentioning

confidence: 99%

A Survey of Brain Tumor Segmentation and Classification Algorithms

Biratu

Schwenker

Ayano³

et al. 2021

J. Imaging

View full text Add to dashboard Cite

show abstract

“…The authors examined their method on the performance of a U-Net model in feature extraction of Cityscapes dataset and showed that the initial convolutional layers exhibit low-level edge-like feature extractions. Grad-CAM based approaches were also used to visualize 2-dimensional [6,26] and 3-dimensional brain tumor segmentation [27].…”

Section: Discussionmentioning

confidence: 99%

“…Already available in the Keras method libraries, Grad-CAM methods have demonstrated great capabilities in image region discrimination in various clinical and computer vision studies [25][26][27][28]. Despite the utility of Grad-CAM, there are some limitations associated with gradient-based explanation and Grad-CAM estimations, especially when targeting multiple objects in an image.…”

Section: Discussionmentioning

confidence: 99%

Explainable Artificial Intelligence for Human-Machine Interaction in Brain Tumor Localization

Esmaeili

Vettukattil

Banitalebi

et al. 2021

JPM

View full text Add to dashboard Cite

Primary malignancies in adult brains are globally fatal. Computer vision, especially recent developments in artificial intelligence (AI), have created opportunities to automatically characterize and diagnose tumor lesions in the brain. AI approaches have provided scores of unprecedented accuracy in different image analysis tasks, including differentiating tumor-containing brains from healthy brains. AI models, however, perform as a black box, concealing the rational interpretations that are an essential step towards translating AI imaging tools into clinical routine. An explainable AI approach aims to visualize the high-level features of trained models or integrate into the training process. This study aims to evaluate the performance of selected deep-learning algorithms on localizing tumor lesions and distinguishing the lesion from healthy regions in magnetic resonance imaging contrasts. Despite a significant correlation between classification and lesion localization accuracy (R = 0.46, p = 0.005), the known AI algorithms, examined in this study, classify some tumor brains based on other non-relevant features. The results suggest that explainable AI approaches can develop an intuition for model interpretability and may play an important role in the performance evaluation of deep learning models. Developing explainable AI approaches will be an essential tool to improve human–machine interactions and assist in the selection of optimal training methods.

show abstract

“…A measure related to completeness was defined in [43] and aimed to capture the proportion of training images represented by the learned visual concepts, in addition to two other metrics: the inter-and intraclass diversity and the faithfulness of explanations computed by perturbing relevant patches and measuring the drop in classification confidence. Other articles followed a similar approach to validate relevant pixels or features identified with a transparent method; for example, in [83] a deletion curve was constructed by plotting the dice score vs. the percentage of pixels removed and [1] defined a recall rate when the model proposes certain number of informative channels. [111] proposed to evaluate the consistency of visualization results and the outputs of a CNN by computing the L1 error between predicted class scores and explanation heatmaps.…”

Section: R: Reportingmentioning

confidence: 99%

“…Segmentation was another major application field (n=9). Research about transparency mainly focused on segmentation problems for brain and cardiac MRIs [33,39,42,83,73,75,91]. Other segmentation problems included mass segmentation in mammograms [86], cardiac segmentation in ultrasound [73], liver tumor segmentation in hepatic CT images, and skin lesion segmentation in dermatological images [34].…”

Section: T: Taskmentioning

confidence: 99%

INTRPRT: A Systematic Review of and Guidelines for Designing and Validating Transparent AI in Medical Image Analysis

Chen¹,

Gómez²,

Huang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Transparency in Machine Learning (ML), including interpretable or explainable ML, attempts to reveal the working mechanisms of complex models, including deep neural networks. Transparent ML promises to advance human factors engineering goals of human-centered AI, such as increasing trust or reducing automation bias, in the target users. However, a core requirement in achieving these aims is that the method is indeed transparent to the users. From a human-centered design perspective, transparency is not a property of the ML model but an affordance, i. e., a relationship between algorithm and user; as a result, iterative prototyping and evaluation with users is critical to attaining adequate solutions that afford transparency. However, following human-centered design principles in highly specialized and high stakes domains, such as healthcare and medical image analysis, is challenging due to the limited availability of and access to end users, such as domain experts, providers, or patients. This dilemma is further exacerbated by the high knowledge imbalance between ML designers and those end users, which implies an even greater need for iterated development.To investigate the state of transparent ML in medical image analysis, we conducted and now present a systematic review of the literature. Our review reveals multiple severe shortcomings in the design and validation of transparent ML for medical image analysis applications. We find that most studies to date approach transparency as a property of the model itself, similar to task performance, without considering end users during neither development nor evaluation. Despite the considerable difference between the roles and knowledge of ML developers and clinical stakeholders, no study reported formative user research to inform the design and development of transparent ML models; moreover, only a few studies validated transparency claims through empirical user evaluations. The oversight of considering ML transparency as a relationship with end users, the lack of user research, and the sporadic validation of transparency claims put contemporary research on transparent ML for medical image analysis at risk of being incomprehensible to users, and thus, clinically irrelevant. To alleviate these shortcomings in forthcoming research while acknowledging the challenges of human-centered design in healthcare, we introduce the INTRPRT guideline, a systematic design directive for transparent ML systems in medical image analysis. To bridge the disconnect between ML system designers and end users and avoid misspending costly development efforts on models that are finally validated as non-transparent to end users, the INTRPRT guideline suggests formative user research as the first step of transparent model design to understand user needs and domain requirements. Following this process produces evidence to support * Joint first authors.Preprint. Under review.

show abstract

Visual interpretability in 3D brain tumor segmentation network

Cited by 42 publications

References 26 publications

A Survey of Brain Tumor Segmentation and Classification Algorithms

A Survey of Brain Tumor Segmentation and Classification Algorithms

Explainable Artificial Intelligence for Human-Machine Interaction in Brain Tumor Localization

INTRPRT: A Systematic Review of and Guidelines for Designing and Validating Transparent AI in Medical Image Analysis

Contact Info

Product

Resources

About