Abstract 2594
Background
Identifying low risk of disease recurrence in localised ccRCC is key for gatekeeping in the adjuvant therapy enrolment. Uncertainty increases the number of patients required for accrual to achieve statistical power. Current scoring systems are good at identifying very low and very high risk cohorts, but have not been proved to be as effective at accurately predicting disease recurrence in intermediate groups. These patients are perhaps those likely to benefit from intervention in addition to surgery, but many may be treated unnecessarily. Using digital pathology, image analysis and machine learning we sought to stratify for risk in this intermediate category.
Methods
Definiens Tissue studio and Developer XD were utilised for object thresholding to measure tumour cell nuclear morphological features on H&E digitised images from 120 ccRCC training set from UK and 217 ccRCC validation set from Singapore. Multiplexed immunofluorescence (mIF) was performed on 120 cases to co-detect neo-vasculature and pan-T cells. An algorithm was derived to measure spatial relationships between blood vessels and T cells. A statistical model was developed by generalised linear model with spatially adaptive local smoothing algorithm, having specificity prefixed (0.8-1) plus cross validation.
Results
Replacing manual nuclear grade with AI aided tumour cell nuclear morphological features improved the specificity of Leibovich score (LS) from 0.76 to 0.86 and from 0.84 to 0.94 in training and validation sets, respectively. Moreover, tumour microenvironment (TM) parameters significantly improved the specificity up to 0.93 in the training set. The negative predictive values of both LS 5 and 6 were zero, but by applying the algorithm the specificity for LS 5 and 6 cases became 0.93 and 0.40 respectively.
Conclusions
By applying image analysis it is possible to identify lower risk for recurrence patients in a conventionally identified intermediate risk group based on routine ccRCC H&E images, and multiplexed TM features. This approach to pathology should help refine selection of patients for clinical trials and form the basis of future AI-enabled prognostic and predictive algorithms in ccRCC.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
Authors.
Funding
Renal Cancer Research Fund and NHS Lothian.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
4096 - Patient experience and use of an intervention combining nurse-led telephone and technologies for the monitoring of oral cancer medication
Presenter: Marie Ferrua
Session: Poster Display session 3
Resources:
Abstract
6042 - Harnessing nurse leadership to implement a project for electronic scheduling of chemotherapy
Presenter: Emma Masters
Session: Poster Display session 3
Resources:
Abstract
3123 - Turkish Cancer Patients’ Preference for Information and Communication Technologies
Presenter: Esra ildes
Session: Poster Display session 3
Resources:
Abstract
6062 - Unmet Needs in Oncology Research related to radiological response evaluation: a multi-center survey in three European countries
Presenter: Sophie Nisse Durgeat
Session: Poster Display session 3
Resources:
Abstract
6109 - A program implementation to facilitate intraoperative brachytherapy between hospitals
Presenter: Marc Garcia Casellas
Session: Poster Display session 3
Resources:
Abstract
1772 - Using Mobile-Based Health Care Applications Outcomes: Mini Systematic Review
Presenter: Aydanur Aydin
Session: Poster Display session 3
Resources:
Abstract
2792 - Evaluation of an education program for cancer patients receiving chemotherapy
Presenter: Iraqi Amina
Session: Poster Display session 3
Resources:
Abstract
3715 - iGestSaúde: Application for self-management of symptoms during chemotherapy treatment
Presenter: Bruno Magalhaes
Session: Poster Display session 3
Resources:
Abstract
3854 - Palliative care requirements of cancer patients and investigation of knowledge and expectations related to palliative care of the patients and their families
Presenter: Ozlem Topkaya
Session: Poster Display session 3
Resources:
Abstract
4997 - Hospice care, what to expect? An exploration of the expectation of future hospice patients
Presenter: Merel van Klinken
Session: Poster Display session 3
Resources:
Abstract