Automated multimodal spectral histopathology for quantitative diagnosis of residual tumour during basal cell carcinoma surgery

Abstract

Multimodal spectral histopathology (MSH), an optical technique combining tissue auto-fluorescence (AF) imaging and Raman micro-spectroscopy (RMS), was previously proposed for detection of residual basal cell carcinoma (BCC) at the surface of surgically-resected skin tissue. Here we report the development of a fully-automated prototype instrument based on MSH designed to be used in the clinic and operated by a non-specialist spectroscopy user. The algorithms for the AF image processing and Raman spectroscopy classification had been first optimised on a manually-operated laboratory instrument and then validated on the automated prototype using skin samples from independent patients. We present results on a range of skin samples excised during Mohs micrographic surgery, and demonstrate consistent diagnosis obtained in repeat test measurement, in agreement with the reference histopathology diagnosis. We also show that the prototype instrument can be operated by clinical users (a skin surgeon and a core medical trainee, after only 1-8 hours of training) to obtain consistent results in agreement with histopathology. The development of the new automated prototype and demonstration of inter-instrument transferability of the diagnosis models are important steps on the clinical translation path: it allows the testing of the MSH technology in a relevant clinical environment in order to evaluate its performance on a sufficiently large number of patients.

Keywords: (170.0170) Medical optics and biotechnology; (170.3880) Medical and biological imaging; (300.6450) Spectroscopy, Raman.

Fig. 1

a). Schematic description of the intended use of MSH for checking completeness of tumour removal during BCC surgery (Mohs surgery and wide-local excision). b) Flow chart describing the automated measurement and diagnosis algorithms for MSH. c) Photographs of the manual Laboratory Instrument and the automated MSH Prototype. The tissue specimen is loaded in a purpose-built cassette with a quartz bottom window (2.5mm x 2.5cm, 1mm thick). The cassette is manually placed on the microscope stage of the Laboratory Instrument or loaded into the Prototype Instrument.

Fig. 2

Optimisation and evaluation of segmentation algorithms for AF images of skin samples (recorded on Laboratory Instrument). a)-c) two typical examples: a) AF images; b) segmentation optimisation functions: f_A = N, where N = segment number; f_B = N*A, where A = area fraction captured by segments; c) segmentation images and quality parameters corresponding to the AF when using the Maxf_A (A) and Maxf_B (B) as intensity thresholds. Scale bars: 5mm. d) Statistical analysis of parameters $\rho$ and $\epsilon$ based on AF images recorded on the Laboratory Instrument on 35 tissue samples with BCC (23 patients).

Fig. 3

Evaluation of sampling points for Raman spectroscopy based on segmentation of AF images (Config. 2). Sample 1: typical sample containing BCC, Sample 2: the sample with the highest number of segments with BCC missed by the allocated sampling points. a) AF images; b) segmented images and sampling points using uniform distribution: pink points represent Raman measurements performed on healthy tissue and white points represent Raman measurements performed on BCC. The number of segments containing BCC detected and missed are indicated for each sample; Scale bars: 5mm. c) evaluation of tumour “Hit rate” and missed segments for: sampling points allocated selectively: sampling point at the position of the lowest and highest intensity within each segment, and uniform distribution of the remaining sampling points (Config. 1); sampling points distributed uniformly within segments (Config. 2).

Fig. 4

Development of the Raman classification model for BCC. a) annotation of Raman spectra based on histopathology following k means clustering of Raman spectra collected by raster scanning; Scale bar: 0.5mm. b) Selected Raman spectra at the location indicated by arrows and coloured coded symbols in the annotated Raman map and circles in the adjacent H&E image.

Fig. 5

Development of the Raman classification model for BCC. a) Average Raman spectra of BCC, healthy skin tissue structures and surgical dye. The spectral features selected for the ANN classifier are highlighted (red lines represent the local baseline); b) confusion matrix for the 5-fold cross validation on the training set of samples measured on the Laboratory instrument. Class EMI includes epidermis, muscle and inflammation.

Fig. 6

Transferability testing of the optimised models on the automated MSH Prototype. a) typical examples of AF images and segmentation results; Scale bars: 5mm. b) statistical analysis of the performance parameters $\rho$, $\epsilon$, hit rate and number of BCC segments missed; c) confusion matrix of the Raman model applied on independent samples; d) 5-fold cross-validation of the joint training and test sets as a function of patient numbers.

Fig. 7

Comparison between MSH diagnosis (automated Prototype instrument) and the corresponding histopathology sections for typical skin layers excised during Mohs micrographic surgery. The diagnosis was based on the algorithm optimised on the training samples measured on the Laboratory Instrument. Sample 1 and 2 are BCC-positive and Sample 3 is BCC-negative. Tumours are encircled in blue circles and false positive segments in Sample 3 are highlighted by black arrows (circles and arrows were added manually).

Fig. 8

Consistency of MSH diagnosis using the automated Prototype instrument. Sample 1 and 2 are BCC-positive and Sample 3 is BCC negative. Tumours are encircled in blue circles and false positive segments in Sample 3 are highlighted by black arrows (circles and arrows were added manually).

Fig. 9

Consistency of MSH diagnosis among different users. User 1: spectroscopy specialist (R. Boitor), User 2: Mohs surgeon (S. Varma) with 1 h training, User 3 (B. Salence): core medical trainee with interest in dermatology (BS) with 8 hours training. Tumours are encircled in blue circles and false positive segments in Sample 3 are highlighted by black arrows (circles and arrows were added manually).