Early experience with Watson for Oncology: a clinical decision-support system for prostate cancer treatment recommendations

Yu, Seong Hyeon; Kim, Myoung Soo; Chung, Ho Seok; Hwang, Eu Chang; Kang, Taek Won; Kwon, Dongdeuk

doi:10.1007/s00345-020-03214-y

Cited by 22 publications

(17 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, deep learning based on convolutional neural networks to automatically learn representative features from raw medical images has been used in different specialties, 8 including radiology, 9 , 10 dermatology, 11 ophthalmology, 12 pathology, 13 , 14 and oncology. 15 , 16 As neural networks can perform very well on segmentation tasks, they have been proposed to facilitate radiotherapy, especially for contouring of organs at risk 17–21 and tumors. 22–25 In particular, convolutional U-Net and DeepMedic architecture have been utilized for brain metastasis segmentation.…”

mentioning

confidence: 99%

Randomized multi-reader evaluation of automated detection and segmentation of brain tumors in stereotactic radiosurgery with deep neural networks

Xiao

Cheng

et al. 2021

Neuro-Oncology

View full text Add to dashboard Cite

Background Stereotactic radiosurgery (SRS), a validated treatment for brain tumors, requires accurate tumor contouring. This manual segmentation process is time-consuming and prone to substantial inter-practitioner variability. Artificial intelligence (AI) with deep neural networks have increasingly been proposed for use in lesion detection and segmentation but have seldom been validated in a clinical setting. Methods We conducted a randomized, cross-modal, multi-reader, multi-specialty, multi-case study to evaluate the impact of AI assistance on brain tumor SRS. A state-of-the-art auto-contouring algorithm built on multi-modality imaging and ensemble neural networks was integrated into the clinical workflow. Nine medical professionals contoured the same case series in two reader modes (assisted or un-assisted) with a memory washout period of 6 weeks between each section. The case series consisted of ten algorithm-unseen cases, including five cases of brain metastases, three of meningiomas and two of acoustic neuromas. Among the nine readers, three experienced experts determined the ground truths of tumor contours. Results With the AI assistance, the inter-reader agreement significantly increased (Dice similarity coefficient [DSC] from 0.86 to 0.90, P<0.001). Algorithm-assisted physicians demonstrated a higher sensitivity for lesion detection than un-assisted physicians (91.3% versus 82.6%, P=0.030). AI assistance improved contouring accuracy, with an average increase in DSC of 0.028, especially for physicians with less SRS experience (average DSC from 0.847 to 0.865, P=0.002). In addition, AI assistance improved efficiency with a median of 30.8%-time savings. Less-experienced clinicians gained prominent improvement on contouring accuracy but less benefit in reduction of working hours. By contrast, SRS specialists had a relatively minor advantage in DSC, but greater timesaving with the aid of AI. Conclusions Deep learning neural networks can be optimally utilized to improve accuracy and efficiency for the clinical workflow in brain tumor SRS.

show abstract

mentioning

confidence: 99%

Randomized multi-reader evaluation of automated detection and segmentation of brain tumors in stereotactic radiosurgery with deep neural networks

Xiao

Cheng

et al. 2021

Neuro-Oncology

View full text Add to dashboard Cite

show abstract

“…The majority of published studies regard-ing CDSS systems for PCa support, concern computer-aided diagnosis systems based on PSA, 21 or patient characteristics (e.g., weight, height, age, and if smoking). 22,23 To the best of our knowledge, however, a similar CDSS based on mpMRI-U/S fusion technology for supporting and improving PCa screening and follow-up like the proposed PCaGuard system has not been reported in the literature.…”

Section: Background and Significancementioning

confidence: 99%

PCaGuard: A Software Platform to Support Optimal Management of Prostate Cancer

et al. 2022

View full text Add to dashboard Cite

Background and Objective Prostate cancer (PCa) is a severe public health issue and the most common cancer worldwide in men. Early diagnosis can lead to early treatment and long-term survival. The addition of the multiparametric magnetic resonance imaging in combination with ultrasound (mpMRI-U/S fusion) biopsy to the existing diagnostic tools improved prostate cancer detection. Use of both tools gradually increases in every day urological practice. Furthermore, advances in the area of information technology and artificial intelligence have led to the development of software platforms able to support clinical diagnosis and decision-making using patient data from personalized medicine. Methods We investigated the current aspects of implementation, architecture, and design of a health care information system able to handle and store a large number of clinical examination data along with medical images, and produce a risk calculator in a seamless and secure manner complying with data security/accuracy and personal data protection directives and standards simultaneously. Furthermore, we took into account interoperability support and connectivity to legacy and other information management systems. The platform was implemented using open source, modern frameworks, and development tools. Results The application showed that software platforms supporting patient follow-up monitoring can be effective, productive, and of extreme value, while at the same time, aiding toward the betterment medicine clinical workflows. Furthermore, it removes access barriers and restrictions to specialized care, especially for rural areas, providing the exchange of medical images and patient data, among hospitals and physicians. Conclusion This platform handles data to estimate the risk of prostate cancer detection using current state-of-the-art in eHealth systems and services while fusing emerging multidisciplinary and intersectoral approaches. This work offers the research community an open architecture framework that encourages the broader adoption of more robust and comprehensive systems in standard clinical practice.

show abstract

“…The similarities and deviations of each pair of answers were evaluated by independent urooncology specialists and reported according to previous publications on Watson for Oncology by IBM (Fig 2) [9][10][11][12]16]:…”

Section: Fig 1 Flow Chart Patient Cohort With Prostate Carcinomamentioning

confidence: 99%

Validation and implementation of a mobile app decision support system for quality assurance of tumor boards. Analyzing the concordance rates for prostate cancer from a multidisciplinary tumor board of a University Cancer Center

Ural

Elter

Yilmaz

et al. 2022

Preprint

View full text Add to dashboard Cite

Background: Certified Cancer Centers must present all patients in multidisciplinary tumor boards (MTD), including standard cases with well-established treatment strategies. Too many standard cases can absorb much of the available time, which can be unfavorable for the discussion of complex cases. In any case, this leads to a high quantity, but not necessarily a high quality of tumor boards Objective: Our aim was to develop a partially algorithm-driven decision support system (DSS) for smart phones to provide evidence-based recommendations for first-line therapy of common urological cancers. To assure quality, we compared each single digital decision with recommendations of an experienced MTD and obtained the concordance. Design, setting and participants : 1873 prostate cancer patients presented in the MTD of the urological department of the University Hospital of Cologne from 2014 to 2018 have been evaluated. Outcome measurements and statistical analysis: Patient characteristics included age, disease stage, Gleason Score, PSA and previous therapies. The questions addressed to MTD were again answered using DSS. All blinded pairs of answers were assessed for discrepancies by independent reviewers. Results and limitations: Overall concordance rate was 99.1% (1856/1873). Stage specific concordance rates were 97.4% (stage I), 99.2% (stage II), 100% (stage III), and 99.2% (stage IV). Quality of concordance were independent of age and risk profile. Conclusions: The reliability of any DSS is the key feature before implementation in clinical routine. Although our system appears to provide this safety, we are now performing cross-validation with several clinics to further increase decision quality and avoid potential clinic bias. Patient summary: The quality of therapeutic decisions provided in tumor boards is perhaps the most relevant criterion for optimal cancer outcome. This tool aims to provide optimal recommendations, to assess the quality on a case-by-case basis and furthermore to objectively display the quality of oncological care.

show abstract

Early experience with Watson for Oncology: a clinical decision-support system for prostate cancer treatment recommendations

Cited by 22 publications

References 23 publications

Randomized multi-reader evaluation of automated detection and segmentation of brain tumors in stereotactic radiosurgery with deep neural networks

Randomized multi-reader evaluation of automated detection and segmentation of brain tumors in stereotactic radiosurgery with deep neural networks

PCaGuard: A Software Platform to Support Optimal Management of Prostate Cancer

Validation and implementation of a mobile app decision support system for quality assurance of tumor boards. Analyzing the concordance rates for prostate cancer from a multidisciplinary tumor board of a University Cancer Center

Contact Info

Product

Resources

About